Towards Future Oriented Collaborative Policy Development for Rural Areas and People

Ulman, Milos; Šimek, Pavel; Masner, Jan; Kogut, Pavel; Löytty, Tuula; Crehan, Patrick; Charvát, Karel; Oliva, A.; Bergheim, Stein Runar; Kalaš, Milan; Kolokol, Denis; Sabbatini, Tommaso

doi:10.7160/aol.2020.120110

Cited by 6 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Creating a model is thus the cornerstone of scenario generation, yet it has long been a labor-intensive task [8,9]. Several works have brought automation to this process [18,19], in particular by deriving models from an evidence base consisting of a text corpus [25][26][27][28]. The recent work of Feblowitz and colleagues at IBM [29] is the closest to our approach in numerous regards: starting from a set seed of concepts (or 'risk forces'), it automatically fetches documents (multiple times daily via the Watson Discovery service) and uses a Q&A system powered by Hugging Face's Transformers to extract a model, noting when concepts can be deemed equivalent.…”

Section: Findings and Implicationsmentioning

confidence: 99%

“…This reflects a broader trend in future studies, which leverages unstructured data from websites, news posts, or academic journals [21][22][23][24]. These text collections have primarily been analyzed through web scrapping and topic modeling; recent examples include [25][26][27][28]. However, none of these studies fully automated the end-to-end process of scenario generation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatically Generating Scenarios from a Text Corpus: A Case Study on Electric Vehicles

2022

View full text Add to dashboard Cite

Creating ‘what-if’ scenarios to estimate possible futures is a key component of decision-making processes. However, this activity is labor intensive as it is primarily done manually by subject-matter experts who start by identifying relevant themes and their interconnections to build models, and then craft diverse and meaningful stories as scenarios to run on these models. Previous works have shown that text mining could automate the model-building aspect, for example, by using topic modeling to extract themes from a large corpus and employing variations of association rule mining to connect them in quantitative ways. In this paper, we propose to further automate the process of scenario generation by guiding pre-trained deep neural networks (i.e., BERT) through simulated conversations to extract a model from a corpus. Our case study on electric vehicles shows that our approach yields similar results to previous work while almost eliminating the need for manual involvement in model building, thus focusing human expertise on the final stage of crafting compelling scenarios. Specifically, by using the same corpus as a previous study on electric vehicles, we show that the model created here either performs similarly to the previous study when there is a consensus in the literature, or differs by highlighting important gaps on domains such as government deregulation.

show abstract

Section: Findings and Implicationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatically Generating Scenarios from a Text Corpus: A Case Study on Electric Vehicles

2022

View full text Add to dashboard Cite

show abstract

“…Therefore, public policies targeting these problems are crucial. Yet, the EU rural policy does not respond to these needs [9].…”

Section: Introductionmentioning

confidence: 99%

EU Rural Policy’s Capacity to Facilitate a Just Sustainability Transition of the Rural Areas

2021

View full text Add to dashboard Cite

The sustainability transition of rural areas is a must due to rapid climate changes and biodiversity loss. Given the limited resources of rural communities, policy should facilitate a just sustainability transition of the EU rural areas. The analysis of EU development policies, past performance and the envisaged scope of reform, presented in this study point to a serious inconsistency between the declaration and implementation of relevant policies. Namely, the marginal role rural areas perform in common agricultural policy and cohesion policy; a result of the lack of a complex approach to rural development. The analysis was based on the concept of good governance and took a multi-level perspective. It advocates territorial justice as an approach that should be at the core of creating a comprehensive policy for rural areas in the EU, including their diversity and empowering local communities to choose the transition pathway that is most in line with their current situation and development capacity. This analysis fills a gap in research on the evolution of the rural development policy in the EU. This research can inform the reprioritization and intensification of efforts to create equitable policies for EU rural development.

show abstract

Evaluating Landscape Attractiveness with Geospatial Data, A Case Study in Flanders, Belgium

Vannoppen

Degerickx

Gobin

2021

Land

View full text Add to dashboard Cite

Attractive landscapes are diverse and resilient landscapes that provide a multitude of essential ecosystem services. The development of landscape policy to protect and improve landscape attractiveness, thereby ensuring the provision of ecosystem services, is ideally adapted to region specific landscape characteristics. In addition, trends in landscape attractiveness may be linked to certain policies, or the absence of policies over time. A spatial and temporal evaluation of landscape attractiveness is thus desirable for landscape policy development. In this paper, landscape attractiveness was spatially evaluated for Flanders (Belgium) using landscape indicators derived from geospatial data as a case study. Large local differences in landscape quality in (i) rural versus urban areas and (ii) between the seven agricultural regions in Flanders were found. This observed spatial variability in landscape attractiveness demonstrated that a localized approach, considering the geophysical characteristics of each individual region, would be required in the development of landscape policy to improve landscape quality in Flanders. Some trends in landscape attractiveness were related to agriculture in Flanders, e.g., a slight decrease in total agricultural area, decrease in dominance of grassland, maize and cereals, a decrease in crop diversity, sharp increase in the adoption of agri-environmental agreements (AEA) and a decrease in bare soil conditions in winter. The observed trends and spatial variation in landscape attractiveness can be used as a tool to support policy analysis, assess the potential effects of future policy plans, identify policy gaps and evaluate past landscape policy.

show abstract

Towards Future Oriented Collaborative Policy Development for Rural Areas and People

Cited by 6 publications

References 9 publications

Automatically Generating Scenarios from a Text Corpus: A Case Study on Electric Vehicles

Automatically Generating Scenarios from a Text Corpus: A Case Study on Electric Vehicles

EU Rural Policy’s Capacity to Facilitate a Just Sustainability Transition of the Rural Areas

Evaluating Landscape Attractiveness with Geospatial Data, A Case Study in Flanders, Belgium

Contact Info

Product

Resources

About